A number of proteins and nucleic acids have been explored as therapeutic targets. These targets are subjects of interest in different areas of biomedical and pharmaceutical research and in the development and evaluation of bioinformatics, molecular modeling, computer-aided drug design and analytical tools. A publicly accessible database that provides comprehensive information about these targets is therefore helpful to the relevant communities. The Therapeutic Target Database (TTD) is designed to provide information about the known therapeutic protein and nucleic acid targets described in the literature, the targeted disease conditions, the pathway information and the corresponding drugs/ligands directed at each of these targets. Cross-links to other databases are also introduced to facilitate the access of information about the sequence, 3D structure, function, nomenclature, drug/ligand binding properties, drug usage and effects, and related literature for each target. This database can be accessed at http://xin.cz3.nus.edu.sg/group/ttd/ttd.asp and it currently contains entries for 433 targets covering 125 disease conditions along with 809 drugs/ligands directed at each of these targets. Each entry can be retrieved through multiple methods including target name, disease name, drug/ligand name, drug/ligand function and drug therapeutic classification.

No abstract

No abstract

In recent years recurrent neural network language models (RNNLMs) have been successfully applied to a range of tasks including speech recognition. However, an important issue that limits the quantity of data used, and their possible application areas, is the computational cost in training. A significant part of this cost is associated with the softmax function at the output layer, as this requires a normalization term to be explicitly calculated. This impacts both the training and testing speed, especially when a large output vocabulary is used. To address this problem, noise contrastive estimation (NCE) is explored in RNNLM training. NCE does not require the above normalization during both training and testing. It is insensitive to the output layer size. On a large vocabulary conversational telephone speech recognition task, a doubling in training speed on a GPU and a 56 times speed up in test time evaluation on a CPU were obtained.

No abstract

In recent years, recurrent neural network language models (RNNLMs) have become increasingly popular for a range of applications including speech recognition. However, the training of RNNLMs is computationally expensive, which limits the quantity of data, and size of network, that can be used. In order to fully exploit the power of RNNLMs, efficient training implementations are required. This paper introduces an open-source toolkit, the CUED-RNNLM toolkit, which supports efficient GPU-based training of RNNLMs. RNNLM training with a large number of word level output targets is supported, in contrast to existing tools which used class-based output-targets. Support fot N-best and lattice-based rescoring of both HTK and Kaldi format lattices is included. An example of building and evaluating RNNLMs with this toolkit is presented for a Kaldi based speech recognition system using the AMI corpus. All necessary resources including the source code, documentation and recipe are available online 1 .

Envelope methodology can provide substantial efficiency gains in multivariate statistical problems, but in some applications the estimation of the envelope dimension can induce selection volatility that may mitigate those gains. Current envelope methodology does not account for the added variance that can result from this selection. In this article, we circumvent dimension selection volatility through the development of a weighted envelope estimator. Theoretical justification is given for our estimator and validity of the residual bootstrap for estimating its asymptotic variance is established. A simulation study and an analysis on a real data set illustrate the utility of our weighted envelope estimator.

No abstract